Learning Graph Neural Networks with Noisy Labels
This addresses robustness in graph classification for machine learning practitioners, but it is incremental as it adapts existing techniques to a specific domain.
The paper tackles the problem of training Graph Neural Networks (GNNs) with symmetric label noise by combining neural message-passing models with loss correction methods, resulting in improved test accuracy under artificial noisy settings.
We study the robustness to symmetric label noise of GNNs training procedures. By combining the nonlinear neural message-passing models (e.g. Graph Isomorphism Networks, GraphSAGE, etc.) with loss correction methods, we present a noise-tolerant approach for the graph classification task. Our experiments show that test accuracy can be improved under the artificial symmetric noisy setting.